A Connectionist Thematic Grid Predictor for Pre-parsed Natural Language Sentences

摘要

Inspired on psycholinguistics and neuroscience, a symbolic-connectionist hybrid system called θ-PRED (Thematic PREDictor for natural language) is proposed, designed to reveal the thematic grid assigned to a sentence. Through a symbolic module, which includes anaphor resolution and relative clause processing, a parsing of the input sentence is performed, generating logical formulae based on events and thematic roles for Portuguese language sentences. Previously, a morphological analysis is carried out. The parsing displays, for grammatical sentences, the existing readings and their thematic grids. In order to disambiguate among possible interpretations, there is a connectionist module, comprising, as input, a featural representation of the words (based on verboun WordNet classification and on classical semantic microfeature representation), and, as output, the thematic grid assigned to the sentence. 0-Pred employs biologically inspired training algorithm and architecture, adopting a psycholinguistic view of thematic theory.